Optimal Robot Manipulation
Chelsea discusses the process of using a dynamics model to derive an optimal policy for robot manipulation tasks. She explains how the algorithm extends beyond simple movements to include object manipulation and locomotion. By generating data through a linear model, the approach facilitates supervised learning for deep networks, ultimately determining the best actions for given observations.In this clip
From this podcast

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Robotic Perception and Control with Chelsea Finn - #29
Related Questions